Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8759
    Prev
    Next
    INDEX
    Explanations

    mention instances of conversion, transformation, or translation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    552
    +0.11
    0.5%
    647
    +0.10
    0.5%
    608
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.04
    647
    +0.10
    0.03
    552
    +0.10
    0.03
    Negative Logits
    Reviewed
    -0.93
    FactoryReloaded
    -0.85
    ritz
    -0.73
    rogen
    -0.70
    UGH
    -0.70
    cation
    -0.70
    heed
    -0.68
    review
    -0.68
    cens
    -0.67
    ablishment
    -0.67
    POSITIVE LOGITS
     usable
    1.17
     concrete
    0.84
     tangible
    0.83
     equivalents
    0.78
     practical
    0.73
     actual
    0.72
     useful
    0.71
     meaningful
    0.69
     cheaper
    0.68
     dollars
    0.67
    Activations Density 0.137%

    No Known Activations